.png){kind=icon}
Return
Tuned Compositional Feature Replays for Efficient Stream Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2023.3344085.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Our brains extract durable, generalizable knowledge from transient experiences of the world. Artificial neural networks come nowhere close to this ability. When tasked with learning to classify objects by training on nonrepeating video frames in temporal order (online stream learning), models that learn well from shuffled datasets catastrophically forget old knowledge upon learning new stimuli. We propose a new continual learning algorithm, compositional replay using memory blocks (CRUMB), which mitigates forgetting by replaying feature maps reconstructed by combining generic parts. CRUMB concatenates trainable and reusable memory block vectors to compositionally reconstruct feature map tensors in convolutional neural networks (CNNs). Storing the indices of memory blocks used to reconstruct new stimuli enables memories of the stimuli to be replayed during later tasks. This reconstruction mechanism also primes the neural network to minimize catastrophic forgetting by biasing it toward attending to information about object shapes more than information about image textures and stabilizes the network during stream learning by providing a shared feature-level basis for all training examples. These properties allow CRUMB to outperform an otherwise identical algorithm that stores and replays raw images while occupying only 3.6% as much memory. We stress-tested CRUMB alongside 13 competing methods on seven challenging datasets. To address the limited number of existing online stream learning datasets, we introduce two new benchmarks by adapting existing datasets for stream learning. With only 3.7%-4.1% as much memory and 15%-43% as much runtime, CRUMB mitigates catastrophic forgetting more effectively than the state-of-the-art. Our code is available at https://github.com/MorganBDT/crumb.git
Keywords:
Brain-inspired replay
catastrophic forgetting
deep learning
stream learning
Journal
IF:
8.9
Papers:
7.6K
Citations:
7.2W
Organization
Cited Papers
ShareSaveShareSaveWHY THERE ARE COMPLEMENTARY LEARNING-SYSTEMS IN THE HIPPOCAMPUS AND NEOCORTEX - INSIGHTS FROM THE SUCCESSES AND FAILURES OF CONNECTIONIST MODELS OF LEARNING AND MEMORY.png)
PSYCHOLOGICAL REVIEW
PSYCHOLOGICAL REVIEWIF5.8
PREAI
ShareSaveA highly stereoselective, catalytic four-component synthesis of dispiroindolo-pyrrolidines/-imidazolidines via azomethine ylidesTetrahedron
TetrahedronIF0
PREAI
ShareSaveComparison of test methods for the determination of delamination in glued laminated timberBioResourcesOAAI
BioResourcesIF0
OAAIShareSave
ShareSave
View more